Scaling World Models @1x_tech Prev: Founding Team @LumaLabsAI, PhD (Dropout 😶🌫️) @UofT, @AIatMeta, @Mila_Quebec 🇨🇦
San Francisco, CA
- Tweets 3,818
- Following 298
- Followers 6,030
- Likes 97,479
Pinned Tweet
I am SO excited to be sharing that I am joining @BerntBornich and @1x_tech to lead the new 1X World Model Lab aimed at building the next frontier of embodied AI! The core guiding principle of the lab is: scale up along every damn axis!! 🚀
Robotics data is NOT a second-class citizen - it is too important of a problem to be left to fine tuning! Your model needs to see your most important tokens from step 0
We need to think about robotics through the first principles of AI: how do we best utilize the vast amounts of web-scale media and how do we create a data-flywheel to collect millions of hours of rich robot interactions. There is no other moat in AI outside of data and @1x_tech has done an INCREDIBLE job scaling manufacturing, production and hardware to build humanoid robots that can create a unique data-flywheel in unstructured environments. Scaling data collection for highly dexterous on-policy robot data will be the only way for creating a moat in AI. @JackMonas and team have made great progress in building World Models, and now the goal is to supercharge this effort by starting a hyper-focused scale and data-pilled lab.
Before scaling compute / data / models, we are currently RAPIDLY scaling our team and hiring across the 4 core pillars of AI: model + data, data infra, ML infra and evals. Looking for folks that are excited about the 0->1 problem and share the same principles as us. There’s a single application for everyone in the lab - if you’re a good at engineering and ML, we will find a place for you in the team ❤️
AGI won’t be solved by fine-tuning… Let’s build the next frontier of AI together 🚀
My DMs are always open!!
We’re going all in on World Models.
Today we’re launching the 1X World Model Lab.
The bet is simple:
You can’t fine-tune your way to AGI.
And you definitely can’t fine-tune your way to robots that can operate in the physical world.
General-purpose humanoids need models that understand space, motion, objects, causality, affordances, physics, and action before they ever see a specific task.
The frontier is not better VLA wrappers.
The frontier is embodied world models.
The 1X World Model Lab will focus on large-scale embodied world model pretraining: building the most generalizable foundation model for humanoid robots from the ground up.
The next frontier in AI requires scaling:
web-scale media + egocentric human videos + sim + dexterous remote operated robot data + on-policy NEO data → real-world deployment for robot data collection and RL → abundance of data → physical AI
The robot collects data.
The model gets better.
The robot gets better.
Repeat.
To lead this, we brought in one of the best for the mission: @_sam_sinha_ , as Head of World Models.
Sam was a founding research scientist at Luma AI and has been at the frontier of scaling multimodal generative video models his whole career.
If you’re the best in the world at large-scale pretraining, video models, robotics, RL, infra, or data — and you want your models to move atoms, not just pixels — join us.
Send background + evidence of exceptional ability to:
wmlab@1x.tech
We’re building the model that makes autonomous labor real.
64
29
427
101,435
The dab at the end was unexpected and clearly emergent behaviour.
Should we write a report on it?? 👀
10
2
92
8,814
Unfortunately don't have excuses for why NEO can't do dexterous tasks anymore...
Come join the @1x_tech team to build the future of embodied AI (also so that @BerntBornich doesn't get mad at me) !!
4
66
5,780
Hands are how you interact with the physical world, collect data, and get to recursive self improvement!
The new Neo hands have the highest level of dexterity and reliability in the world, and this is the path towards how we get to Embodied AGI!
Introducing NEO’s 25 Degrees of Freedom, tendon-driven hands — nearing or surpassing human-level dexterity, strength, speed, and reliability.
For seventy years, robotics worked around the hand problem. The humanoid bet is the reverse: it lives or dies at the fingertips.
5
2
78
9,683
Preview of one of the main breakthroughs that convinced me that @1x_tech was on the clear path to winning 👀
Stay tuned!!
2
2
120
8,849
Number of image + video models from Meta over the past year: 0
Number of image + video models from Meta over the past month since Jiaming joined: 2
Congrats @baaadas and team!!
Excited to help launch Muse Image / Video @AIatMeta. A few of my images are on the release page.
Creation is moving from "one prompt -> one image" to iterative, agentic systems that plan, use tools, and refine.
ai.meta.com/blog/introducing…
2
2
57
7,861
Samarth Sinha retweeted
already a huge @_sam_sinha_ fan. so excited to have him lead the new 1X World Model Lab :)
he and @BerntBornich sat down with @Forbes earlier this week to talk about the role of the lab in our NEO roadmap and why "you can't fine-tune your way to AGI"
read it here: forbes.com/sites/johnkoetsie…
I am SO excited to be sharing that I am joining @BerntBornich and @1x_tech to lead the new 1X World Model Lab aimed at building the next frontier of embodied AI! The core guiding principle of the lab is: scale up along every damn axis!! 🚀
Robotics data is NOT a second-class citizen - it is too important of a problem to be left to fine tuning! Your model needs to see your most important tokens from step 0
We need to think about robotics through the first principles of AI: how do we best utilize the vast amounts of web-scale media and how do we create a data-flywheel to collect millions of hours of rich robot interactions. There is no other moat in AI outside of data and @1x_tech has done an INCREDIBLE job scaling manufacturing, production and hardware to build humanoid robots that can create a unique data-flywheel in unstructured environments. Scaling data collection for highly dexterous on-policy robot data will be the only way for creating a moat in AI. @JackMonas and team have made great progress in building World Models, and now the goal is to supercharge this effort by starting a hyper-focused scale and data-pilled lab.
Before scaling compute / data / models, we are currently RAPIDLY scaling our team and hiring across the 4 core pillars of AI: model + data, data infra, ML infra and evals. Looking for folks that are excited about the 0->1 problem and share the same principles as us. There’s a single application for everyone in the lab - if you’re a good at engineering and ML, we will find a place for you in the team ❤️
AGI won’t be solved by fine-tuning… Let’s build the next frontier of AI together 🚀
My DMs are always open!!
1
5
46
5,918
Samarth Sinha retweeted
This is going to be fun....excited to scale this up with you @_sam_sinha_!
I am SO excited to be sharing that I am joining @BerntBornich and @1x_tech to lead the new 1X World Model Lab aimed at building the next frontier of embodied AI! The core guiding principle of the lab is: scale up along every damn axis!! 🚀
Robotics data is NOT a second-class citizen - it is too important of a problem to be left to fine tuning! Your model needs to see your most important tokens from step 0
We need to think about robotics through the first principles of AI: how do we best utilize the vast amounts of web-scale media and how do we create a data-flywheel to collect millions of hours of rich robot interactions. There is no other moat in AI outside of data and @1x_tech has done an INCREDIBLE job scaling manufacturing, production and hardware to build humanoid robots that can create a unique data-flywheel in unstructured environments. Scaling data collection for highly dexterous on-policy robot data will be the only way for creating a moat in AI. @JackMonas and team have made great progress in building World Models, and now the goal is to supercharge this effort by starting a hyper-focused scale and data-pilled lab.
Before scaling compute / data / models, we are currently RAPIDLY scaling our team and hiring across the 4 core pillars of AI: model + data, data infra, ML infra and evals. Looking for folks that are excited about the 0->1 problem and share the same principles as us. There’s a single application for everyone in the lab - if you’re a good at engineering and ML, we will find a place for you in the team ❤️
AGI won’t be solved by fine-tuning… Let’s build the next frontier of AI together 🚀
My DMs are always open!!
2
3
57
7,757
I am SO excited to be sharing that I am joining @BerntBornich and @1x_tech to lead the new 1X World Model Lab aimed at building the next frontier of embodied AI! The core guiding principle of the lab is: scale up along every damn axis!! 🚀
Robotics data is NOT a second-class citizen - it is too important of a problem to be left to fine tuning! Your model needs to see your most important tokens from step 0
We need to think about robotics through the first principles of AI: how do we best utilize the vast amounts of web-scale media and how do we create a data-flywheel to collect millions of hours of rich robot interactions. There is no other moat in AI outside of data and @1x_tech has done an INCREDIBLE job scaling manufacturing, production and hardware to build humanoid robots that can create a unique data-flywheel in unstructured environments. Scaling data collection for highly dexterous on-policy robot data will be the only way for creating a moat in AI. @JackMonas and team have made great progress in building World Models, and now the goal is to supercharge this effort by starting a hyper-focused scale and data-pilled lab.
Before scaling compute / data / models, we are currently RAPIDLY scaling our team and hiring across the 4 core pillars of AI: model + data, data infra, ML infra and evals. Looking for folks that are excited about the 0->1 problem and share the same principles as us. There’s a single application for everyone in the lab - if you’re a good at engineering and ML, we will find a place for you in the team ❤️
AGI won’t be solved by fine-tuning… Let’s build the next frontier of AI together 🚀
My DMs are always open!!
We’re going all in on World Models.
Today we’re launching the 1X World Model Lab.
The bet is simple:
You can’t fine-tune your way to AGI.
And you definitely can’t fine-tune your way to robots that can operate in the physical world.
General-purpose humanoids need models that understand space, motion, objects, causality, affordances, physics, and action before they ever see a specific task.
The frontier is not better VLA wrappers.
The frontier is embodied world models.
The 1X World Model Lab will focus on large-scale embodied world model pretraining: building the most generalizable foundation model for humanoid robots from the ground up.
The next frontier in AI requires scaling:
web-scale media + egocentric human videos + sim + dexterous remote operated robot data + on-policy NEO data → real-world deployment for robot data collection and RL → abundance of data → physical AI
The robot collects data.
The model gets better.
The robot gets better.
Repeat.
To lead this, we brought in one of the best for the mission: @_sam_sinha_ , as Head of World Models.
Sam was a founding research scientist at Luma AI and has been at the frontier of scaling multimodal generative video models his whole career.
If you’re the best in the world at large-scale pretraining, video models, robotics, RL, infra, or data — and you want your models to move atoms, not just pixels — join us.
Send background + evidence of exceptional ability to:
wmlab@1x.tech
We’re building the model that makes autonomous labor real.
64
29
427
101,435
Apply for the lab here:
1x.recruitee.com/o/ai-resear…
Blog post about the new lab:
1x.tech/discover/1x-world-mo…
@Forbes article covering the lab:
forbes.com/sites/johnkoetsie…
23
2,098
Samarth Sinha retweeted
📢📢📢 Velox 🚀: Learning Representations of 4D Geometry and Appearance
In our #CVPR2026 paper, we introduce a method for learning a native 4D representation, useful for many downstream tasks, such as video-to-4D, 3D tracking, cloth simulation, and others!
🌐: apple.github.io/ml-velox
📝: arxiv.org/abs/2605.04527
7
54
179
22,367
After 4 incredible years, today marks my last day at @LumaLabsAI. I’m so proud to have helped build the company from 5 to 250 people. Luma started as a humble attempt at bringing NeRFs to smartphones in 2022, and is currently an extremely successful startup capable of training frontier models that can truly compete with the best generative models in the world.
I have so much love and respect for the whole team but I want to give a special thanks to @baaadas - for trusting me 3 years ago and deciding to join Luma and help us be a serious generative AI company, and then for building a culture that allowed me to do my best work ❤️
Finally, I’m so proud of our most ambitious and impressive model release: Uni-1, an industry defining unified multimodal model that will shape the future of the company, and the field for years to come. Working relentlessly on the project with some of my favourite people was the highlight of my career thus far. This project wouldn’t be possible without @shenbokui for his leadership and the rest of the Omni team for the incredible execution and dedication to the mission 🚀
Will take a week off to visit 🇨🇦 but have some exciting updates to share soon after 👀
17
3
204
12,969
So excited to share that Uni 1.1 is out on API and on LMArena!!
A model competitive with ones from GDM+OAI for a fraction of the cost 😍
Uni-1 and Uni-1-Max are flagship intelligent image generation, editing and reference models that will shape the creative industry 🔥
Exciting news: UNI-1.1-Max and UNI-1.1 debuts making @LumaLabsAI the #3 lab in the Image Arena across both Text-to-Image and Image Edit! These are versions released without agentic search.
Text-to-Image Arena
- UNI-1.1-Max #6 overall (1193), +12 points over MAI-Image-2
- UNI-1.1 #7 overall (1190), +13 points over Reve-v1.5
Multi-Image Edit Arena
- UNI-1.1-Max #7 overall (1315), +21 points over Seedream 4.5
- UNI-1.1 #8 overall, (1298)
Single-Image Edit Arena
- UNI-1.1-Max #7 overall (1337)
- UNI-1.1 #11 overall, (1310) on par with Grok-Imagine-Image (20260207)
Congratulations to @LumaLabsAI on this solid performance!
5
14
86
17,320
Read more about it here! lumalabs.ai/api
So proud of what we have been able to accomplish with a tiny fraction of the budget!
1
888
Congrats @ayaanzhaque Alex and the ImageGen team! Clearly the path forward is intelligent image generation!
What makes ChatGPT Images 2.0 a state-of-the-art image generation model?
Researchers behind the model explain. A thread:
Thinking & Intelligence in ChatGPT Images 2.0, demonstrated by @ayaanzhaque
2
26
5,030
Samarth Sinha retweeted
📢 Check out Lyra 2.0: large-scale generative worlds with a 3D-consistent video diffusion model. Optionally, feed-forward 3DGS and/or mesh reconstructions.
Great work by @TianchangS, @xuanchi13, and the rest of the crew. Grateful for my time with all of these brilliant people 🙏
We scaled up Lyra to generate explorable 3D worlds! 🚀
Introducing Lyra 2.0 — turning a single image into a 3D world you can walk through, look back, and even drop a robot into 🤖
Code and Model available today!
🌐 Website: research.nvidia.com/labs/sil…
(1/N)
1
14
67
7,383
The fact that Claude code was built without Claude code is the most impressive thing to me ngl
Claude code source code has been leaked via a map file in their npm registry!
Code: pub-aea8527898604c1bbb12468b…
1
13
1,844